from transformers import AutoImageProcessor, MaskFormerForInstanceSegmentation

>>> from PIL import Image

>>> import requests

​

>>> # load MaskFormer fine-tuned on ADE20k semantic segmentation

>>> image_processor = AutoImageProcessor.from_pretrained("facebook/maskformer-swin-base-ade")

>>> model = MaskFormerForInstanceSegmentation.from_pretrained("facebook/maskformer-swin-base-ade")

​

>>> url = (

...     "https://huggingface.co/datasets/hf-internal-testing/fixtures_ade20k/resolve/main/ADE_val_00000001.jpg"

... )

>>> image = Image.open(requests.get(url, stream=True).raw)

>>> inputs = image_processor(images=image, return_tensors="pt")

​

>>> outputs = model(**inputs)

>>> # model predicts class_queries_logits of shape `(batch_size, num_queries)`

>>> # and masks_queries_logits of shape `(batch_size, num_queries, height, width)`

>>> class_queries_logits = outputs.class_queries_logits

>>> masks_queries_logits = outputs.masks_queries_logits

​

>>> # you can pass them to image_processor for postprocessing

>>> predicted_semantic_map = image_processor.post_process_semantic_segmentation(

...     outputs, target_sizes=[image.size[::-1]]

... )[0]

​

>>> # we refer to the demo notebooks for visualization (see "Resources" section in the MaskFormer docs)

>>> list(predicted_semantic_map.shape)

[512, 683]